INDEX

Explanations

references to male and female pronouns

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

it

-0.70

is

-0.68

-0.67

-0.62

to

-0.61

can

-0.60

are

-0.59

-0.57

↵

-0.55

 have

-0.54

POSITIVE LOGITS

Efq

1.30

 myſelf

1.08

 Majefty

1.07

$_"

1.05

 Monfieur

1.05

 Theſe

1.03

 ―――――

1.02

 Jefus

1.02

 Shakspeare

1.01

 feroit

1.00

Activations Density 0.198%

references to male and female pronouns

No Comments

No Known Activations